Q-GrAM: Fine-Grained Image–Text Retrieval via Grouped Query Routing and Conditional Query Modulation
TL;DR
Experiments show that Q-GrAM achieves strong text-to-image retrieval performance against both global embedding baselines and representative fine-grained image–text matching methods, while maintaining competitive bidirectional retrieval performance.
Abstract
Existing image–text retrieval methods often compute cross-modal similarity using global single-vector representations. Although efficient for coarse semantic alignment, such compressed representations are limited when textual queries involve fine-grained semantics, including objects, attributes, relations, and their compositional structures. This paper focuses on fine-grained text-to-image retrieval and proposes Q-GrAM, a retrieval-oriented adaptation of the BLIP-2 Q-Former. Instead of treating Q-Former queries as a homogeneous set, Q-GrAM partitions a fixed query budget into semantically differentiated groups. A text-guided router assigns token-level semantic demands to query groups, while query conditional initialization modulates each group according to group-level textual summaries. The resulting grouped visual query features are matched with text tokens through a group-aware late interaction scorer, and auxiliary routing balance and inter-group diversity regularization are introduced to stabilize semantic specialization. Experiments on MS-COCO 5K, Flickr30K, and Flickr30K-CFQ show that Q-GrAM achieves strong text-to-image retrieval performance against both global embedding baselines and representative fine-grained image–text matching methods, while maintaining competitive bidirectional retrieval performance. These results demonstrate the effectiveness of structured, text-conditioned Q-Former query specialization for fine-grained text-driven image search.